29 lines
1.2 KiB
Python
29 lines
1.2 KiB
Python
import re
|
|
|
|
# Pricing per 1M tokens in USD
|
|
MODEL_PRICING = [
|
|
(r"gemini-2\.5-flash-lite", {"input_per_mtok": 0.075, "output_per_mtok": 0.30}),
|
|
(r"gemini-2\.5-flash", {"input_per_mtok": 0.15, "output_per_mtok": 0.60}),
|
|
(r"gemini-3-flash-preview", {"input_per_mtok": 0.15, "output_per_mtok": 0.60}),
|
|
(r"gemini-3\.1-pro-preview", {"input_per_mtok": 3.50, "output_per_mtok": 10.50}),
|
|
(r"claude-.*-sonnet", {"input_per_mtok": 3.0, "output_per_mtok": 15.0}),
|
|
(r"claude-.*-opus", {"input_per_mtok": 15.0, "output_per_mtok": 75.0}),
|
|
(r"deepseek-v3", {"input_per_mtok": 0.27, "output_per_mtok": 1.10}),
|
|
]
|
|
|
|
def estimate_cost(model: str, input_tokens: int, output_tokens: int) -> float:
|
|
"""
|
|
Estimate the cost of a model call based on input and output tokens.
|
|
Returns the total cost in USD.
|
|
"""
|
|
if not model:
|
|
return 0.0
|
|
|
|
for pattern, rates in MODEL_PRICING:
|
|
if re.search(pattern, model, re.IGNORECASE):
|
|
input_cost = (input_tokens / 1_000_000) * rates["input_per_mtok"]
|
|
output_cost = (output_tokens / 1_000_000) * rates["output_per_mtok"]
|
|
return input_cost + output_cost
|
|
|
|
return 0.0
|